Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    responsibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     пользу
    1.27
    farbe
    1.20
    是
    1.18
    હેર
    1.15
    ro
    1.13
    AY
    1.13
    nog
    1.12
     enkele
    1.12
    OM
    1.11
     imprescind
    1.10
    POSITIVE LOGITS
    ות
    1.63
    ों
    1.31
    ता
    1.28
    রাও
    1.27
    ർ
    1.26
    ية
    1.21
    ibilities
    1.21
    ին
    1.17
    ان
    1.16
    ன்
    1.15
    Act Density 0.008%

    No Known Activations